Conversation
Adds an OSS-Fuzz project for the safetensors Rust crate, which is widely used to load model-weight files across the ML ecosystem and is not currently fuzzed. A libFuzzer target exercises SafeTensors::deserialize, the untrusted-input entry point that parses the 8-byte little-endian header length, the JSON metadata header, and each tensor's (dtype, shape, offset) descriptors against the backing buffer. Built and run locally with infra/helper.py (build_fuzzers --sanitizer address; run_fuzzer smoke test).
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
|
ahkarl13 is integrating a new project: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This adds an OSS-Fuzz integration for safetensors, the Rust crate used across the ML ecosystem to load model-weight files. It is not currently in OSS-Fuzz.
Target: a libFuzzer harness on
SafeTensors::deserialize— the untrusted-input entry point that parses the 8-byte little-endian header length, the JSON metadata header, and each tensor's(dtype, shape, [begin,end))offset descriptors against the backing buffer. The header-length / offset math is the classic out-of-bounds seam for memory-format deserializers.Validated locally:
python3 infra/helper.py build_fuzzers --sanitizer address safetensors— builds clean.python3 infra/helper.py run_fuzzer safetensors deserialize— ~353k exec/s over a 90s smoke run; the corpus reaches the header/offset parser (dictionary picks updata_offsets,dtype,shape,__metadata__). No crashes in the smoke run.Details:
cargo-fuzz), libFuzzer + AddressSanitizer, x86_64.primary_contact/auto_ccs: ahkarl13@gmail.com